Everyone, I am working on 6D pose estimation and I have to predict a rotation matrix (Euler angle) and translation. Now In Pascal Voc annotations are in the form of azimuth, elevation and distance from object pose are given. And intrinsic parameters of the camera is given for each image per object in the image.
Now please help as I don't know how to convert these azimuths, elevation to Euler and how to find the translation for model training for 6D pose estimation.
Or please rectify me if I am understanding this in the wrong direction.